Building the inference layer as the primary enterprise operating layer.
"We build open-source tools at the intersection of AI agents, cybersecurity, and local inference — with a bias toward production-grade security, Apple Silicon optimization, and agentic automation."
| Repo | What it does |
|---|---|
| TSLIT | Time-Shift LLM Integrity Tester — detects affiliation bias and time-based logic bombs in local LLMs (3,840 interactions/model) |
| pentest-regulatory-intel | RegIntel — AI-powered pentest regulation inventory across 20+ jurisdictions with reflection quality gates |
| strixresearch | Research and documentation for the Strix autonomous AI pentesting platform |
| agentic-ai-pentesting | Book companion — two approaches to AI-assisted pentesting (autonomous platform + Burp Suite co-pilot) |
| NVD-Extractor | Extract critical network-attack-vector CVEs from the NVD API, filtered for Linux/Windows/external APIs |
| skillspector-trial | Skillspector — single-file offline scanner grading Agent Skills A–F on security + quality (the static evidence stream for oscal-skills-guardrails) |
| strix-omlx | Points the Strix autonomous pentest agent at a local OMLX MLX server (abliterated MiniMax-M2) — fully local, LiteLLM routing; companion to strixresearch |
| Repo | What it does |
|---|---|
| oscal-agent-guardrails | OSCAL profiles as a policy brain to guardrail LLM agents at runtime (allow/deny/needs_approval) |
| oscal-digital-twin-playground | Digital twin drift detection — SSP vs live config, with risk assessment and mitigation |
| oscal-zero-trust-lens | Zero Trust coverage analysis across 7 dimensions from SP 800-53 controls |
| oscal-agent-lab | Multi-agent lab — RAG Q&A, SSP diff, profile generation, validation over 1,196 controls |
| oscal-cac-playgd | Compliance-as-code CLI — explain OSCAL files, suggest remediation, PR-style diff review |
| genai-regulatory-intel | RegIntel-AgenticAI — autonomous GenAI regulatory intelligence across 16 global financial jurisdictions (LangGraph 4-agent state machine) |
| oscal-skills-guardrails | OSCAL-as-policy for Agent Skills — dual-evidence admission (static scan + local LLM rubric judge), digest integrity, CI gate, assessment-results audit trail |
| driftlab | Runtime compliance observer — diffs a live agent's decision traces against a certified OSCAL baseline, proves drift via sandboxed micro-experiments, emits OSCAL 1.1.2 assessment-results (CA-7) |
| Repo | What it does |
|---|---|
| agent-stack | Interactive 10-layer architecture visualization for reliable AI agents (vis.js) |
| deepagent-azure-cli | Turnkey coding assistant CLI — Azure OpenAI + LangChain DeepAgents, Textual TUI, HITL |
| N8n2langraph | Convert n8n workflow JSON into standalone LangGraph Python scripts |
| sst-autoresearch | Speaker voice dynamics analysis via Karpathy-style autoresearch loop (Takens' embedding, Lyapunov) |
| project-pulse-sap | SAP implementation onboarding — meetings → transcription → LLM wiki → podcast |
| AutogenRequirementsAgent | Experiment in strict JSON inter-agent messaging with nested GroupChat and local Ollama LLMs |
| wiki-vs-rag | Four-arm benchmark over the sw30labs wiki — single-shot RAG vs agentic-RAG vs wiki-nav vs QMD; agentic-RAG wins Pareto |
| langgraph-checkpoints-vs-stores | Runnable offline reference — thread-scoped checkpoints vs cross-thread stores, real StateGraph/InMemorySaver/InMemoryStore, CI-gated |
| venture-pathfinder | Scans local repos into a Neo4j graph, then LangGraph + a Fabric-style Pattern Engine (local OMLX) surfaces recurring patterns and white-space venture paths |
| Repo | What it does |
|---|---|
| tars-ai | TARS from Interstellar as a local voice agent — LLM + TTS served by a local OMLX server (OpenAI protocol), zero cloud |
| screenlens | Video scene intelligence — hybrid keyframe detection, Qwen3.5-VL captioning, ChromaDB search |
| qwenbench-mlx | Benchmark suite for Qwen 3.5 family (0.8B→35B) with auto-judge and cost-efficiency scoring |
| mlx-distillation-explained | Educational distillation PoC — Claude Sonnet → Llama 3.1 8B via LoRA on Apple Silicon |
| mlx-responses-api-server | OpenAI/Azure/Anthropic-compatible local inference server with tool calling (renamed from local-mlx-responsesAPI-server) |
| audiobook_generator | Book → audiobook conversion using Qwen3-TTS + LangGraph with QA verification |
| QWEN3-VL-Python-OCR-Script-MLX | Batch image captioning with Qwen3-VL-30B on MLX |
| MLX-YouTubeScribe | YouTube transcription using local Whisper models with Streamlit UI |
| deepseekvl2-PDF-OCR-private | Local PDF OCR using DeepSeek-VL2 MoE on NVIDIA CUDA |
| bonsai-image-ternary-4b-mlx-2bit | Local Apple Silicon wrapper for Bonsai 4B ternary-quantized image generation |
| lance-3b-video-bf16 | Local MLX text-to-video + video Q&A (Lance 3B via lance-mlx runtime) |
| stable-audio-3 | Stability AI audio/music generation — 433M CPU models to 1.4B CUDA, Gradio UI |
| sulphur-2-base | Local MLX video generation wrapper for Sulphur 2 via ltx-2-mlx runtime |
| supertonic-3-mlx | Local MLX TTS for Supertonic 3 — JSON graph topology + NPZ weights |
| dflash-mlx-trial | DFlash × MLX — block-diffusion speculative decoding for Qwen3.6-27B on Apple Silicon (~3.4× faster, identical output) |
| STTbench | Benchmarks speech-to-text on cost/speed/accuracy — OpenAI gpt-4o-transcribe vs local MLX Whisper, WER split into sub/del/ins |
| ace-step-1.5-mlx | Local Apple Silicon text-to-song (with vocals) wrapper for ACE-Step 1.5 |
| ltx-2.3-mlx | Local MLX text/image/audio-to-video for Lightricks LTX 2.3 |
| longcat-video-avatar-1.5-mlx | Local MLX talking-avatar video (portrait + audio + prompt) |
| Repo | What it does |
|---|---|
| gitnexus_fleet | Clone, index (KuzuDB graph), and query entire GitHub orgs via MCP + web dashboard |
| AutogenDocGenerator | AutoGen-powered repo documentation generator with GroupChat agents |
| AutogenMermaidGenerator | AutoGen GroupChat source code → Mermaid diagram generator |
| OllamaPDF2Markdown | PDF → Markdown via Ollama multimodal models (Mistral Small 3.1 24B) |
| RepoBundle | Export/import Git repos as single human-readable text files |
| Word-to-Markdown-Converter | .docx → Markdown converter preserving headings, lists, tables |
| animated-GIF-Creator | Image folder or MOV → animated GIF with auto-resize |
| nemotron-parse-spark | NVIDIA Nemotron Parse v1.2 harness for DGX Spark (Grace Blackwell GB10) — PDF → structured text + bounding boxes |
AI Agents in Cybersecurity — A Practitioner's Guide, from Strategy to Implementation.
How autonomous agents are transforming enterprise security — from automating SOC operations and incident triage to building multi-agent defense systems. Includes real-world case studies, practical frameworks, and a hands-on lab companion.
Built by Nic Cravino · AI/ML Engineering · Cybersecurity · Enterprise Automation